Enframing The World

Gestell has solved search-based reasoning Mar 31th, 2025

LLMs were made to be tools of knowledge and intelligence, not to search through messy databases. The current Retrieval Augmented Generation (’RAG‘) tooling that exists expects LLMs to be experts at search, and it resultantly fails to achieve results. Fundamentally, RAG is an overwhelming task for an LLM, the attempt to find truth in data devolves as more context of ’similar chunks‘ are shoved into a transformer, degrading the quality of the attention ranking mechanism

Of Categories Mar 13th, 2025

Categorization is the process by which the possible contents of thought are first organized prior to cognition. There is an infinite diversity of content in the world that requires ordering to be represented and understood. The contents of cognition when lent to disorder and unstructured representation fail to communicate truth, leading to crude understanding and confusion. Cognition rests upon the synthesis of raw content and structured categories...

Gestell - Best in world at FinanceBench Mar 4th, 2025

Gestell is best in the world at FinanceBench by Patronus AI with a score of 88% - outperforming the closest competition by ~30% Not only did we beat FinanceBench on the ‘Shared Vector Store’ setting which lets an LLM reason across an entire database, we beat also FinanceBench at its ‘Oracle’ results which gave the model the exact page containing the answer for context...

Enframing and Disclosure Feb 18th, 2025

Disclosure names the process of the opening of the world to intelligibility. Reasoning is the process of making sense of and determining truths from the open intelligibility of the world. Machinic reasoning fails not when the world is unintelligible, but rather when the process of Disclosure has failed in opening the world as such. At Gestell, we call Disclosure the process by which Enframed data is made available to and used by LLMs...